樸素貝葉斯算法C--代碼有截圖(共7頁)

1、精選優(yōu)質(zhì)文檔-傾情為你奉上#include #include #include #include /_getcwd(), _chdir()#include /_MAX_PATH, system()#include /_finddata_t, _findfirst(), _findnext(), _findclose()char vocabulary100020;/*聲明公有二維數(shù)組，用來存儲分割好的單詞*/*=將要分類的文本分割成單詞存儲在二維數(shù)組vocabulary中=*/輸入?yún)?shù)：要分類的文本/輸出參數(shù)：該文本中總單詞數(shù)int SplitToWord(char text)int i=0;c

2、har seps=, .n; /*定義單詞的分隔符*/ char *substring; /*利用分隔符將文本內(nèi)容分割成單詞并存儲*/substring=strtok(text,seps); while(substring!=NULL) strcpy(vocabularyi,substring);/將單詞存儲到vocabulary數(shù)組中 substring=strtok(NULL,seps); i+;return i; /返回一共多少個單詞/*=計算該目錄下的文件數(shù)=*/輸入?yún)?shù)：無/輸出參數(shù)：該目錄下.txt文件數(shù)int CountDirectory()int count=0; /txt文件

3、計數(shù)器long hFile; _finddata_t fileinfo;/*查找.txt文件，記錄文件數(shù)*/ if (hFile=_findfirst(*.txt,&fileinfo)!=-1L) do count+; while (_findnext(hFile,&fileinfo) = 0);return count;/*=計算某類別中P(ai|vj)=*/輸入?yún)?shù)：分類文本中單詞數(shù)/輸出參數(shù)：該類別下P(ai|vj)float CalculateWordProbability(int wordCount)int countSame; /分類文本中的某單詞在所有訓(xùn)練樣本中出現(xiàn)次數(shù)int c

4、ountAll=0; /訓(xùn)練樣本中總單詞數(shù)char token;FILE *fp;float wordProbability=1; /為后面聯(lián)乘做準(zhǔn)備int i,j;long hFile; _finddata_t fileinfo;for(j=0;jwordCount;j+) /對于分類樣本中的每一個單詞 countSame=0; countAll=0; if(hFile=_findfirst(*.txt,&fileinfo)!=-1L) /對于該類別下每一個.txt文本 do if(fp=fopen(,r)=NULL) /是否能打開該文本 printf(Sorry!

5、Cannot open the file!n); exit(0); /*存儲此.txt文件中每個單詞并與分類文本的單詞作比較*/ while(token = fgetc(fp) != EOF) char keyword1024; i = 0; keyword0 = token; / 將每個詞第一個字符賦給數(shù)組第一個元素 while (keyword+i = fgetc(fp) != & keywordi != t & keywordi != EOF & keywordi != n); / 開始讀字符，直到遇到空白符，說明找到一個詞 keywordi = 0;/ 加結(jié)束符 countAll+;

6、if (strcmp(keyword,vocabularyj) = 0) /比較兩個單詞是否相同 countSame+; fclose(fp); while (_findnext(hFile,&fileinfo) = 0); wordProbability*=(float)(countSame+1)/(float)(wordCount+countAll)*300; /計算P(wj|vi)，為了擴(kuò)大效果而*380return wordProbability; /*=計算每個類別的最終概率輸出結(jié)果=*/輸入?yún)?shù)：分類文本中單詞數(shù) void CalculateProbability(int word

7、Count)/*將類別表存儲在二維數(shù)組中*/FILE *fp;char classList1020; /類別列表 char ch; /臨時讀取字符使用 int index=0; /classList的行標(biāo) int className_c=0; /classList的列標(biāo)if(fp=fopen(ClassList.txt,r)=NULL) printf(Failed to open the file: ClassList.txt.n); ch = fgetc(fp); while(ch!=EOF) if(ch!=n) classListindexclassName_c=ch; className

8、_c+; else classListindexclassName_c=0; index+; className_c=0; ch = fgetc(fp);/*計算總文本數(shù)和每個類別下的文本數(shù)、P(ai|vj)*/int txtCount10; /每個類別下的訓(xùn)練文本數(shù)int countAll=0; /訓(xùn)練集中總文本數(shù)float wordProbability10; /每個類別的單詞概率，即P(ai|vj)if(_chdir(c:SogouCSample1) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount0=CountDirectory(); /獲取該類別

9、下.txt文件數(shù) countAll+=txtCount0; wordProbability0=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(c:SogouCSample2) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount1=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount1; wordProbability1=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_ch

10、dir(c:SogouCSample3) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount2=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount2; wordProbability2=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(c:SogouCSample4) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount3=CountDirectory(); /獲取該類別下.txt文件數(shù) countA

11、ll+=txtCount3; wordProbability3=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(c:SogouCSample5) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount4=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount4; wordProbability4=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(c:SogouCSam

12、ple6) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount5=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount5; wordProbability5=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(c:SogouCSample7) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount6=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount6;

13、wordProbability6=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(C:SogouCSample8) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount7=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount7; wordProbability7=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(C:SogouCSample9) /更改當(dāng)前絕對路徑

14、 printf(系統(tǒng)找不到指定路徑!n);else txtCount8=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount8; wordProbability8=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)if(_chdir(C:SogouCSample10) /更改當(dāng)前絕對路徑 printf(系統(tǒng)找不到指定路徑!n);else txtCount9=CountDirectory(); /獲取該類別下.txt文件數(shù) countAll+=txtCount9; wordProbabilit

15、y9=CalculateWordProbability(wordCount); /獲取該類別下P(wj|vi)/*計算先驗(yàn)概率和最終概率并輸出分類結(jié)果*/float max=0;int classNo=0;float priorProbability10;float finalProbability10;for(int i=0;imax) /找到最大概率并記錄 max=finalProbabilityi; classNo=i; printf(該文本為類別%s的概率為:%.5en,classListi,finalProbabilityi); /輸出每個類別的最終概率printf(n經(jīng)分析，該文本

16、最有可能為%s類文本!n,classListclassNo); /輸出最后分類結(jié)果/*=調(diào)用文本分割函數(shù)和計算最終概率函數(shù)=*/輸入?yún)?shù)：分類文本void NaiveBayesClassifier(char text)int vocabularyCount;/分類樣本中單詞數(shù)vocabularyCount=SplitToWord(text); /對要分類的文本進(jìn)行單詞分割，結(jié)果存儲在vocabulary數(shù)組中，返回分類樣本中單詞數(shù)CalculateProbability(vocabularyCount); /計算最終概率/*=程序入口=*/int main()char text=Microso

17、ft offered 44.6 billion dollars to buy Yahoo.February 1st network reported the Associated Press news, Microsoft offered 44.6 billion dollars in cash and stock to buy Yahoo search site.Microsoft offered to pay 31 dollars per share for Yahoo.Microsofts acquisition offer on Jan. 31 premium of 62% than Yahoos closing price of 19.18 dollars.Microsoft said that Yahoo shareholders can choose cash or stock transactions. Microsoft and Yahoo have sought cooperation in late 2006 and early 2007.The last two years, Yahoo has been in a dilemma: the market share decline,poor operating performance,st